|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM371148804 |
| 003 |
DE-627 |
| 005 |
20241004232038.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240417s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3389030
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1557.xml
|
| 035 |
|
|
|a (DE-627)NLM371148804
|
| 035 |
|
|
|a (NLM)38625774
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhang, Ruonan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Bridging Visual and Textual Semantics
|b Towards Consistency for Unbiased Scene Graph Generation
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 03.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Scene Graph Generation (SGG) aims to detect visual relationships in an image. However, due to long-tailed bias, SGG is far from practical. Most methods depend heavily on the assistance of statistics co-occurrence to generate a balanced dataset, so they are dataset-specific and easily affected by noises. The fundamental cause is that SGG is simplified as a classification task instead of a reasoning task, thus the ability capturing the fine-grained details is limited and the difficulty in handling ambiguity is increased. By imitating the way of dual process in cognitive psychology, a Visual-Textual Semantics Consistency Network (VTSCN) is proposed to model the SGG task as a reasoning process, and relieve the long-tailed bias significantly. In VTSCN, as the rapid autonomous process (Type1 process), we design a Hybrid Union Representation (HUR) module, which is divided into two steps for spatial awareness and working memories modeling. In addition, as the higher order reasoning process (Type2 process), a Global Textual Semantics Modeling (GTS) module is designed to individually model the textual contexts with the word embeddings of pairwise objects. As the final associative process of cognition, a Heterogeneous Semantics Consistency (HSC) module is designed to balance the type1 process and the type2 process. Lastly, our VTSCN raises a new way for SGG model design by fully considering human cognitive process. Experiments on Visual Genome, GQA and PSG datasets show our method is superior to state-of-the-art methods, and ablation studies validate the effectiveness of our VTSCN
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a An, Gaoyun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hao, Yiqing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wu, Dapeng Oliver
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 11 vom: 15. Okt., Seite 7102-7119
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:11
|g day:15
|g month:10
|g pages:7102-7119
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3389030
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 46
|j 2024
|e 11
|b 15
|c 10
|h 7102-7119
|